def predict(net,test_imgs,ctx,save_fig_path):
test_iter=load_img_batch(test_imgs,64,'test')
num_imgs=len(test_imgs)
#从测试集中猫、狗各取三个样本，用于实测
index_cat=np.random.randint(0,num_imgs/2,size=3)
index_dog=np.random.randint(num_imgs/2,num_imgs,size=3)
index=np.append(index_cat,index_dog)
np.random.shuffle(index)
pred_list=evaluate_accuracy(test_iter,net,ctx,ispred=True)
pred_label=[pred_list[i] for i in index]
true_label=[test_imgs[i][1] for i in index]
print('cat: 0, dog: 1')
print('true label:')
print(np.reshape(true_label,(2,-1)))
print('predict label:')
print(np.reshape(pred_label,(2,-1)))
show_img=[test_imgs[i][0] for i in index]
d2l.show_images(show_img,2,3,scale=1)
plt.savefig(save_fig_path+'\\cat_dog.png')
plt.show()
plt.close()
def pikaqiu():
batch_size, edge_size = 32, 256
train_iter, _ = load_data_pikachu(batch_size, edge_size)
batch = train_iter.next()
print(batch.data[0].shape, batch.label[0].shape)
imgs = (batch.data[0][0:10].transpose((0, 2, 3, 1))) / 255
axes = d2l.show_images(imgs, 2, 5).flatten()
for ax, label in zip(axes, batch.label[0][0:10]):
d2l.show_bboxes(ax, [label[0][1:5] * edge_size], colors=['w'])
train_iter = image.ImageDeIter(
path_imgrec=os.path.join(data_dir, "train.rec"),
path_imgidx=os.path.join(data_dir, 'train.idx'),
batch_size=batch_size,
data_shape=(3, edge_size, edge_size), shuffle=True, rand_crop=1,
min_object_covered=0.95, max_attempts=200)
val_iter = image.ImageDetIter(path_imgrec=os.path.join(data_dir, 'val.rec'), batch_size=batch_size,
data_shape=(3, edge_size, edge_size), suhffle=False)
return train_iter, val_iter
# In[ ]:
batch_size, edge_size = 32, 256
train_iter, _ = load_data_pikachu(batch_size, edge_size)
batch = train_iter.next()
batch.data[0].shape, batch.label[0].shape
# In[ ]:
#画出10张图片和pikachu的bounding_box
imgs = (batch.data[0][0:10].transpose((0, 2, 3, 1))) / 255
axes = d2l.show_images(imgs, 2, 5).flatten()
for ax, label in zip (axes, batch.label[0][0:10]):
d2l.show_bboxes(ax, [label[0][1:5] * edge_size], colors=['w'])
root, 'train.txt' if is_train else 'val.txt')
with open(txt_fname, 'r') as f:
images = f.read().split()
features, labels = [None] * len(images), [None] * len(images)
for i, fname in enumerate(images):
features[i] = image.imread('%s/JPEGImages/%s.jpg' % (root, fname))
labels[i] = image.imread(
'%s/SegmentationClass/%s.png' % (root, fname))
return features, labels
train_features, train_labels = read_voc_images()
n = 5
imgs = train_features[0:n] + train_labels[0:n]
d2l.show_images(imgs, 2, n)
# 该常量已保存在d2lzh包中方便以后使用
VOC_COLORMAP = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
[0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
[64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0],
[64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128],
[0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0],
[0, 64, 128]]
# 该常量已保存在d2lzh包中方便以后使用
VOC_CLASSES = ['background', 'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair', 'cow',
'diningtable', 'dog', 'horse', 'motorbike', 'person',
'potted plant', 'sheep', 'sofa', 'train', 'tv/monitor']
colormap2label = nd.zeros(256 ** 3)
'wd': 1e-3
})
print("start train...\n")
d2l.train(train_iter, test_iter, net, loss, trainer, ctx, num_epochs=1) # 5
print("end train...\n")
#9.10.6-预测像素类别
def predict(img):
X = test_iter._dataset.normalize_image(img)
X = X.transpose((2, 0, 1)).expand_dims(axis=0)
pred = nd.argmax(net(X.as_in_context(ctx[0])), axis=1)
return pred.reshape((pred.shape[1], pred.shape[2]))
#可视化像素的预测类别，映射回数据集中的标注颜色
def label2image(pred):
colormap = nd.array(d2l.VOC_COLORMAP, ctx=ctx[0], dtype='uint8')
X = pred.astype('int32')
return colormap[X, :]
test_images, test_labels = d2l.read_voc_images(is_train=False)
n, imgs = 4, []
for i in range(n):
crop_rect = (0, 0, 480, 320)
X = image.fixed_crop(test_images[i], *crop_rect)
pred = label2image(predict(X))
imgs += [X, pred, image.fixed_crop(test_labels[i], *crop_rect)]
d2l.show_images(imgs[::3] + imgs[1::3] + imgs[2::3], 3, n)
data_dir = '../data'
base_url = 'https://apache-mxnet.s3-accelerate.amazonaws.com/'
fname = gutils.download(base_url + 'gluon/dataset/hotdog.zip',
path=data_dir,
sha1_hash='fba480ffa8aa7e0febbb511d181409f899b9baa5')
with zipfile.ZipFile(fname, 'r') as z:
z.extractall(data_dir)
train_imgs = gdata.vision.ImageFolderDataset(
os.path.join(data_dir, 'hotdog/train'))
test_imgs = gdata.vision.ImageFolderDataset(
os.path.join(data_dir, 'hotdog/test'))
hotdogs = [train_imgs[i][0] for i in range(8)]
not_hotdogs = [train_imgs[-i - 1][0] for i in range(8)]
d2l.show_images(hotdogs + not_hotdogs, 2, 8, scale=1.4)
normalize = gdata.vision.transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
train_augs = gdata.vision.transforms.Compose([
gdata.vision.transforms.RandomResizedCrop(224),
gdata.vision.transforms.RandomFlipLeftRight(),
gdata.vision.transforms.ToTensor(), normalize
])
test_augs = gdata.vision.transforms.Compose([
gdata.vision.transforms.Resize(256),
gdata.vision.transforms.CenterCrop(224),
gdata.vision.transforms.ToTensor(), normalize
])
import d2lzh as d2l
from mxnet import image
from matplotlib import pyplot as plt
batch_size=32
img_size=512
train_iter=image.ImageDetIter(path_imgrec='D:\d2l-zh20200904\data\pikachu\\train.rec',
path_imgidx='D:\d2l-zh20200904\data\pikachu\\train.idx',
batch_size=batch_size,data_shape=(3,img_size,img_size),shuffle=True,rand_crop=1,
min_object_covered=0.95,max_attempts=200)
test_iter=image.ImageDetIter(path_imgrec='D:\d2l-zh20200904\data\pikachu\\val.rec',batch_size=batch_size,data_shape=(3,img_size,img_size),shuffle=False)
batch=train_iter.next()
imgs=batch.data[0].transpose((0,2,3,1))/255
axes=d2l.show_images(imgs,4,8).flatten()
# imgs = (batch.data[0][0:10].transpose((0, 2, 3, 1))) / 255
# axes = d2l.show_images(imgs, 2, 5).flatten()
# for ax, label in zip(axes, batch.label[0][0:10]):
# d2l.show_bboxes(ax, [label[0][1:5] * 256], colors=['w'])
labels=batch.label[0]
for ax,label in zip(axes,labels):
d2l.show_bboxes(ax,[label[0][1:5]*img_size])
plt.show()
